chaiml-ca18-v1-1-dpo

developer_uid: chai_backend_admin

submission_id: chaiml-ca18-v1-1-dpo_v1

model_name: training123

model_group: ChaiML/ca18-v1-1-dpo

status: torndown

timestamp: 2025-11-18T10:21:28+00:00

num_battles: 6063

num_wins: 3165

celo_rating: 1294.09

family_friendly_score: 0.5085999999999999

family_friendly_standard_error: 0.0070700217821446625

submission_type: basic

model_repo: ChaiML/ca18-v1-1-dpo

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 2048

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.6804703009143699, 'latency_mean': 1.4694509601593018, 'latency_p50': 1.4671828746795654, 'latency_p90': 1.6140917539596558}, {'batch_size': 3, 'throughput': 1.2434607992982882, 'latency_mean': 2.4080901098251344, 'latency_p50': 2.4350486993789673, 'latency_p90': 2.59719340801239}, {'batch_size': 5, 'throughput': 1.5194361502188432, 'latency_mean': 3.279636387825012, 'latency_p50': 3.2864540815353394, 'latency_p90': 3.704388642311096}, {'batch_size': 6, 'throughput': 1.5830689064194918, 'latency_mean': 3.7706942701339723, 'latency_p50': 3.7539384365081787, 'latency_p90': 4.272537899017334}, {'batch_size': 8, 'throughput': 1.6964822164498998, 'latency_mean': 4.686251311302185, 'latency_p50': 4.699421048164368, 'latency_p90': 5.389503359794617}, {'batch_size': 10, 'throughput': 1.7613721026460734, 'latency_mean': 5.638186100721359, 'latency_p50': 5.625811338424683, 'latency_p90': 6.39032678604126}]

gpu_counts: {'NVIDIA L40S': 1}

display_name: training123

is_internal_developer: True

language_model: ChaiML/ca18-v1-1-dpo

model_size: 13B

ranking_group: single

throughput_3p7s: 1.58

us_pacific_date: 2025-11-15

win_ratio: 0.5220188025729837

generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', '\n', '</s>', 'You:'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': True}

Resubmit model

Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name chaiml-ca18-v1-1-dpo-v1-mkmlizer
Waiting for job on chaiml-ca18-v1-1-dpo-v1-mkmlizer to finish
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ║                                                                     ║
chaiml-ca18-v1-1-dpo-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ca18-v1-1-dpo-v1-mkmlizer: Downloaded to shared memory in 37.202s
chaiml-ca18-v1-1-dpo-v1-mkmlizer: Checking if ChaiML/ca18-v1-1-dpo already exists in ChaiML
chaiml-ca18-v1-1-dpo-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7mkeytep, device:0
chaiml-ca18-v1-1-dpo-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ca18-v1-1-dpo-v1-mkmlizer: quantized model in 28.167s
chaiml-ca18-v1-1-dpo-v1-mkmlizer: Processed model ChaiML/ca18-v1-1-dpo in 65.370s
chaiml-ca18-v1-1-dpo-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ca18-v1-1-dpo-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ca18-v1-1-dpo-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ca18-v1-1-dpo-v1/nvidia
chaiml-ca18-v1-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ca18-v1-1-dpo-v1/nvidia/config.json
chaiml-ca18-v1-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ca18-v1-1-dpo-v1/nvidia/special_tokens_map.json
chaiml-ca18-v1-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ca18-v1-1-dpo-v1/nvidia/tokenizer_config.json
chaiml-ca18-v1-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ca18-v1-1-dpo-v1/nvidia/tokenizer.json
chaiml-ca18-v1-1-dpo-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ca18-v1-1-dpo-v1/nvidia/flywheel_model.0.safetensors
chaiml-ca18-v1-1-dpo-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 29.45it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 45.33it/s]
Loading 0:   5%|▍         | 17/363 [00:00<00:08, 42.64it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:08, 41.79it/s]
Loading 0:   7%|▋         | 27/363 [00:00<00:07, 42.77it/s]
Loading 0:   9%|▉         | 32/363 [00:00<00:09, 33.39it/s]
Loading 0:  11%|█         | 39/363 [00:00<00:07, 41.09it/s]
Loading 0:  12%|█▏        | 44/363 [00:01<00:07, 40.79it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:07, 40.80it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:07, 42.15it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:07, 42.99it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:11, 27.18it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:08, 35.02it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 33.94it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 37.00it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 39.71it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 35.00it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:07, 34.35it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:07, 33.05it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:06, 37.79it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:06, 41.19it/s]
Loading 0:  32%|███▏      | 117/363 [00:03<00:06, 39.10it/s]
Loading 0:  34%|███▎      | 122/363 [00:03<00:05, 40.21it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:07, 32.82it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 39.13it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 39.08it/s]
Loading 0:  40%|███▉      | 144/363 [00:04<00:08, 25.55it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:07, 27.48it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:06, 31.46it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:06, 30.56it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:05, 37.39it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:05, 37.80it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 38.05it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:04, 38.11it/s]
Loading 0:  51%|█████     | 185/363 [00:05<00:04, 36.13it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:03, 44.09it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:03, 43.99it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 42.65it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 43.64it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 34.45it/s]
Loading 0:  61%|██████    | 221/363 [00:05<00:03, 46.77it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 30.55it/s]
Loading 0:  64%|██████▍   | 232/363 [00:06<00:04, 32.00it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 34.95it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.10it/s]
Loading 0:  68%|██████▊   | 248/363 [00:06<00:03, 35.70it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 42.41it/s]
Loading 0:  72%|███████▏  | 260/363 [00:07<00:02, 42.03it/s]
Loading 0:  73%|███████▎  | 265/363 [00:07<00:02, 42.86it/s]
Loading 0:  74%|███████▍  | 270/363 [00:07<00:02, 44.64it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 36.64it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 42.20it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 40.95it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 40.31it/s]
Loading 0:  82%|████████▏ | 298/363 [00:07<00:01, 39.27it/s]
Loading 0:  83%|████████▎ | 303/363 [00:08<00:01, 41.25it/s]
Loading 0:  85%|████████▍ | 308/363 [00:08<00:02, 24.95it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 25.44it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 34.90it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 36.63it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 38.08it/s]
Loading 0:  93%|█████████▎| 338/363 [00:09<00:00, 44.65it/s]
Loading 0:  95%|█████████▍| 344/363 [00:09<00:00, 42.47it/s]
Loading 0:  96%|█████████▌| 349/363 [00:09<00:00, 43.12it/s]
Loading 0:  98%|█████████▊| 356/363 [00:09<00:00, 47.71it/s]
Loading 0: 100%|█████████▉| 362/363 [00:09<00:00, 43.66it/s]
                                                            
Job chaiml-ca18-v1-1-dpo-v1-mkmlizer completed after 94.04s with status: succeeded
Stopping job with name chaiml-ca18-v1-1-dpo-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.56s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ca18-v1-1-dpo-v1
Waiting for inference service chaiml-ca18-v1-1-dpo-v1 to be ready
Inference service chaiml-ca18-v1-1-dpo-v1 ready after 170.74755597114563s
Pipeline stage MKMLDeployer completed in 171.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.6591498851776123s
Received healthy response to inference request in 1.4914178848266602s
Received healthy response to inference request in 1.8582079410552979s
Received healthy response to inference request in 1.7954423427581787s
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Received healthy response to inference request in 1.4744398593902588s
5 requests
0 failed requests
5th percentile: 1.477835464477539
10th percentile: 1.4812310695648194
20th percentile: 1.4880222797393798
30th percentile: 1.5249642848968505
40th percentile: 1.5920570850372315
50th percentile: 1.6591498851776123
60th percentile: 1.7136668682098388
70th percentile: 1.7681838512420653
80th percentile: 1.8079954624176025
90th percentile: 1.8331017017364502
95th percentile: 1.8456548213958741
99th percentile: 1.855697317123413
mean time: 1.6557315826416015
Pipeline stage StressChecker completed in 9.64s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.71s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.85s
Shutdown handler de-registered
chaiml-ca18-v1-1-dpo_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2298.31s
Shutdown handler de-registered
chaiml-ca18-v1-1-dpo_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-ca18-v1-1-dpo_v1 status is now torndown due to DeploymentManager action